Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    6

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .xml
    -0.08
    |--------------------------------------------------------------------------↵
    -0.08
    .leadingAnchor
    -0.07
    ?("
    -0.07
    <TEntity
    -0.07
    ⇖
    -0.07
     Hazel
    -0.07
                        ↵                    ↵
    -0.07
    ⇞
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     Indeed
    0.08
     gadgets
    0.07
     Hampton
    0.07
     bouts
    0.07
    빪
    0.07
     recher
    0.07
     ]]
    0.07
    гар
    0.07
     besoin
    0.07
     chaque
    0.07
    Act Density 0.001%

    No Known Activations